Publication:
Human action recognition with sparse classification and multiple-view learning

Simple item page
dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Inteligencia Artificial Aplicada (GIAA)es
dc.contributor.authorCilla, Rodrigoes
dc.contributor.authorPatricio Guisado, Miguel Ángeles
dc.contributor.authorBerlanga de Jesús, Antonioes
dc.contributor.authorMolina López, José Manueles
dc.date.accessioned2015-07-14T09:13:43Z
dc.date.available2015-07-14T09:13:43Z
dc.date.issued2014-09
dc.description.abstractEmploying multiple camera viewpoints in the recognition of human actions increases performance. This paper presents a feature fusion approach to efficiently combine 2D observations extracted from different camera viewpoints. Multiple-view dimensionality reduction is employed to learn a common parameterization of 2D action descriptors computed for each one of the available viewpoints. Canonical correlation analysis and their variants are employed to obtain such parameterizations. A sparse sequence classifier based on L1 regularization is proposed to avoid the problem of having to choose the proper number of dimensions of the common parameterization. The proposed system is employed in the classification of the Inria Xmas Motion Acquisition Sequences (IXMAS) data set with successful results.en
dc.description.statusPublicadoes
dc.format.extent11
dc.format.mimetypeapplication/pdf
dc.identifier.bibliographicCitationExpert Systems (2014). 31(4), 354-364en
dc.identifier.doihttps://doi.org/10.1111/exsy.12040
dc.identifier.issn1468-0394 (online)
dc.identifier.issn0266-4720 (print)
dc.identifier.publicationfirstpage354es
dc.identifier.publicationissue4es
dc.identifier.publicationlastpage364es
dc.identifier.publicationtitleExpert systemsen
dc.identifier.publicationvolume31es
dc.identifier.urihttps://hdl.handle.net/10016/21416
dc.identifier.uxxiAR/0000015753
dc.language.isoengen
dc.publisherWileyen
dc.rights© 2013 Wiley Publishing Ltd.en
dc.rights.accessRightsopen accessen
dc.subject.ecienciaInformáticaes
dc.subject.otherHuman Action Recognitionen
dc.subject.otherMultiple View Learningen
dc.subject.otherL1 regularizationen
dc.titleHuman action recognition with sparse classification and multiple-view learningen
dc.typeresearch article*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
human_ES_2014_ps.pdf
Size:
4.1 MB
Format:
Adobe Portable Document Format
Download
Collections
DI - GIAA - Artículos de Revistas